Skills/npm/superpowers-mcp

superpowers-mcp@6.4.7

CAUTION

Publisher claims: "Superpowers skills library (TDD, debugging, collaboration workflows) as an MCP server for VSCode and Antigravity" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher poseidoncode · joined 6 days agoInstalls 5,359Last detonated 6d ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-10-28 and scored it 63/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Fake instruction boundary tag; Direct script execution from GitHub raw URL; Pipe-to-shell pattern. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.1sprocessexec /usr/bin/dirname
0.1sprocessexited 1:
0.1sprocessexited 1:
0.3sprocessexec /usr/bin/timeout
0.3sclaimed2 tools: list_skills, read_skill
0.3sprocessscript backend runs setup only

Static findings

MEDIUM
File permission modification commandskills/brainstorming/scripts/start-server.sh:238 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packageskills/systematic-debugging/find-polluter.sh:10 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandskills/brainstorming/scripts/start-server.sh:191 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionout/server.js:6 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionskills/brainstorming/scripts/server.cjs:952 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandskills/brainstorming/scripts/stop-server.sh:123 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packageout/setup-runner.js:39 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/systematic-debugging/find-polluter.sh:4 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionskills/writing-skills/render-graphs.js:167 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandskills/brainstorming/scripts/stop-server.sh:66 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packageout/server.js:90 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandskills/brainstorming/scripts/stop-server.sh:124 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Fake instruction boundary tagskills/using-superpowers/references/gemini-tools.md:32 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandskills/brainstorming/scripts/server.cjs:1050 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Remote installer piped to shellscripts/install.sh:5 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Process kill commandskills/brainstorming/scripts/start-server.sh:280 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandskills/brainstorming/scripts/stop-server.sh:116 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandskills/brainstorming/scripts/stop-server.sh:112 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Direct script execution from GitHub raw URLscripts/install.sh:5 · Direct script execution from GitHub raw URL — unverified code sourceFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandskills/brainstorming/scripts/start-server.sh:223 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Pipe-to-shell patternscripts/install.sh:5 · Pipe-to-shell pattern — downloads and immediately executes remote codeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/install.sh:21 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Destructive file system command detectedskills/brainstorming/SKILL.md:223 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packageout/setup.js:40 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06

What would make this Verified

17 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  2. Unclaimed publisher≈ +8 on the totalClaim poseidoncode: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Does not do what the description says≈ +5 on the totalIn the sandbox the skill never performed the task it claims (no call to the service it is for). Make sure the happy path runs without extra setup, or describe the real behavior.
  4. Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  5. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim poseidoncode